Probabilistic vehicle trajectory prediction via driver characteristic and intention estimation model under uncertainty

Abstract

Purpose For autonomous vehicles, trajectory prediction of surrounding vehicles is beneficial to improving the situational awareness of dynamic and stochastic traffic environments, which is a crucial and indispensable element to realize highly automated driving. Design/methodology/approach In this paper, the overall framework consists of two parts: first, a novel driver characteristic and intention estimation (DCIE) model is built to indicate the higher-level information of the vehicle using its low-level motion variables; then, according to the estimation results of the DCIE model, a classified Gaussian process model is established for probabilistic vehicle trajectory prediction under different motion patterns. Findings The whole method is later applied and analyzed in the highway lane-change scenarios with the parameters of models learned from the public naturalistic driving data set. Compared with other traditional methods, the performance of this proposed approach is proved superior, demonstrated by the higher accuracy in the long prediction horizon and a more reasonable description of uncertainty. Originality/value This hierarchical approach is proposed to make trajectory prediction accurately both in the short term and long term, which can also deal with the uncertainties caused by the perception system or indeterminate vehicle behaviors.

Passing‐yielding intention estimation during lane change conflict: A semantic‐based Bayesian inference method

“…Based on the construction of the DBN model, our research applies Gaussian distributions to model the conditional probability relationship between nodes. Gaussian distribution is a commonly applied probability model for PGM-based research [15,16]. The passing-yielding intentions are inferred with the Bayesian formula and forwardbackward algorithm.…”

“…We compared the prediction accuracy between SIIE-based prediction and baseline method, whose estimation output is the merging and straight-going intentions measured by DBN [16]. To integrate with PF-based trajectory prediction, the merging intention describes the following motion modals: before the merging intention is identified, MV and SV should drive within their initial lane.…”

“…Koenig et al [15] applied DBN to estimate lane change intention, by analysing the influencing factors on driver's intention. Liu et al [16] proposed an integrated approach to measure driver's characteristics and lane-changing intentions. DBN is a probabilistic graphical model, whose structure is designed with two aspects: the relationships between factors within a time frame and the transitive relations between adjacent time frames.…”

Driving Style-Based Conditional Variational Autoencoder for Prediction of Ego Vehicle Trajectory

“…However, only longitudinal motion was predicted, and NGSIM data were utilized. Liu et al estimated the driving style using a dynamic Bayesian network and predicted the trajectory using a Gaussian process model [13], [14]. The limitation is that they used a naturalistic vehicle trajectory data set called highD [15] which is similar to NGSIM.…”